statsmodels.stats.weightstats.DescrStatsW.get_compare DescrStatsW.get_compare(other, weights=None) [source] return an instance of CompareMeans with self and other Parameters: other : array_like or instance of DescrStatsW If array_like then this creates an instance of DescrStatsW with the given weights. weights : None or array weights are only used if other is not an instance of DescrStatsW Returns: cm : instance of CompareMeans the instance has self attached as d1 and other as d2.

statsmodels.sandbox.regression.gmm.LinearIVGMM.fitgmm LinearIVGMM.fitgmm(start, weights=None, optim_method=None, **kwds) [source] estimate parameters using GMM for linear model Uses closed form expression instead of nonlinear optimizers Parameters: start : not used starting values for minimization, not used, only for consistency of method signature weights : array weighting matrix for moment conditions. If weights is None, then the identity matrix is used optim_method : not used, optim

statsmodels.genmod.generalized_estimating_equations.GEEResults.fittedvalues static GEEResults.fittedvalues() [source] Returns the fitted values from the model.

statsmodels.duration.hazard_regression.PHRegResults.summary PHRegResults.summary(yname=None, xname=None, title=None, alpha=0.05) [source] Summarize the proportional hazards regression results. Parameters: yname : string, optional Default is y xname : list of strings, optional Default is x# for ## in p the number of regressors title : string, optional Title for the top table. If not None, then this replaces the default title alpha : float significance level for the confidence interval

statsmodels.sandbox.regression.gmm.IVGMMResults.compare_j IVGMMResults.compare_j(other) overidentification test for comparing two nested gmm estimates This assumes that some moment restrictions have been dropped in one of the GMM estimates relative to the other. Not tested yet We are comparing two separately estimated models, that use different weighting matrices. It is not guaranteed that the resulting difference is positive. TODO: Check in which cases Stata programs use the same weigths

statsmodels.genmod.families.family.Poisson.deviance Poisson.deviance(endog, mu, scale=1.0) [source] Poisson deviance function Parameters: endog : array-like Endogenous response variable mu : array-like Fitted mean response variable scale : float, optional An optional scale argument Returns: deviance : float The deviance function at (endog,mu) as defined below. Notes If a constant term is included it is defined as

statsmodels.robust.norms.Hampel class statsmodels.robust.norms.Hampel(a=2.0, b=4.0, c=8.0) [source] Hampel function for M-estimation. Parameters: a : float, optional b : float, optional c : float, optional The tuning constants for Hampel?s function. The default values are a,b,c = 2, 4, 8. See also statsmodels.robust.norms.RobustNorm Methods psi(z) The psi function for Hampel?s estimator psi_deriv(z) rho(z) The robust criterion function for Hampel?s estimator weights(z) Hampel weig

statsmodels.regression.mixed_linear_model.MixedLM.information MixedLM.information(params) Fisher information matrix of model Returns -Hessian of loglike evaluated at params.

statsmodels.discrete.discrete_model.MultinomialResults.summary2 MultinomialResults.summary2(alpha=0.05, float_format='%.4f') [source] Experimental function to summarize regression results Parameters: alpha : float significance level for the confidence intervals float_format: string : print format for floats in parameters summary Returns: smry : Summary instance this holds the summary tables and text, which can be printed or converted to various output formats. See also statsmode

statsmodels.genmod.families.links.NegativeBinomial.inverse NegativeBinomial.inverse(z) [source] Inverse of the negative binomial transform Parameters: z : array-like The value of the inverse of the negative binomial link at p. Returns : ??- : p : array Mean parameters Notes g^(-1)(z) = exp(z)/(alpha*(1-exp(z)))